def execute():
test_data = load_npy_file(npy_files_dir_path + 'test_z_data.npy')
test_labels = load_npy_file(npy_files_dir_path + 'test_labels.npy')
one_hot_test_labels = tf.keras.utils.to_categorical(test_labels)
model = tf.keras.models.load_model(model_saving_dir_path + 'model_Z.h5')
loss, acc = model.evaluate(test_data, one_hot_test_labels)
print_loss_acc(loss, acc)
def execute():
test_data = load_npy_file(npy_files_dir_path + 'test_y_data.npy')
test_labels = load_npy_file(npy_files_dir_path + 'test_labels.npy')
one_hot_test_labels = tf.keras.utils.to_categorical(test_labels)
model = tf.keras.models.load_model(model_saving_dir_path + 'model_Y.h5')
loss, acc = model.evaluate(test_data, one_hot_test_labels)
print_loss_acc(loss, acc)
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tf_lite_model = converter.convert()
create_dir_if_necessary(tf_lite_model_saving_dir_path)
open(tf_lite_model_saving_dir_path + 'model_Y.tflite', 'wb').write(tf_lite_model)
def main():
x_train = load_npy_file(npy_files_saving_dir_path + 'train_x_data.npy')
x_val = load_npy_file(npy_files_saving_dir_path + 'valid_x_data.npy')
x_test = load_npy_file(npy_files_saving_dir_path + 'test_x_data.npy')
y_train = load_npy_file(npy_files_saving_dir_path + 'train_labels.npy')
y_val = load_npy_file(npy_files_saving_dir_path + 'valid_labels.npy')
y_test = load_npy_file(npy_files_saving_dir_path + 'test_labels.npy')
print(len(x_train) == len(y_train))
print(len(x_val) == len(y_val))
print(len(x_test) == len(y_test))
def execute():
train_data = load_npy_file(npy_files_dir_path + 'train_z_data.npy')
valid_data = load_npy_file(npy_files_dir_path + 'valid_z_data.npy')
test_data = load_npy_file(npy_files_dir_path + 'test_z_data.npy')
train_labels = load_npy_file(npy_files_dir_path + 'train_labels.npy')
valid_labels = load_npy_file(npy_files_dir_path + 'valid_labels.npy')
test_labels = load_npy_file(npy_files_dir_path + 'test_labels.npy')
one_hot_train_labels = tf.keras.utils.to_categorical(train_labels)
one_hot_valid_labels = tf.keras.utils.to_categorical(valid_labels)
one_hot_test_labels = tf.keras.utils.to_categorical(test_labels)
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(3, activation='softmax')
])
model.compile(
optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy']
)
history = model.fit(
train_data,
one_hot_train_labels,
epochs=20,
batch_size=512,
validation_data=(valid_data, one_hot_valid_labels)
)
create_dir_if_necessary(model_saving_dir_path)
model.save(model_saving_dir_path + 'model_Z.h5')
loss, acc = model.evaluate(test_data, one_hot_test_labels)
print_loss_acc(loss, acc)
show_loss(history)
show_accuracy(history)